[jamendo] Improve

youtube_dl/extractor/extractors.py

@@ -408,7 +408,10 @@ from .ivi import (
 from .ivideon import IvideonIE
 from .iwara import IwaraIE
 from .izlesene import IzleseneIE
-from .jamendo import JamendoIE, JamendoAlbumIE
+from .jamendo import (
+    JamendoIE,
+    JamendoAlbumIE,
+)
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
 from .jwplatform import JWPlatformIE

youtube_dl/extractor/jamendo.py

@@ -2,17 +2,13 @@
 from __future__ import unicode_literals
 
 import re
-from collections import namedtuple
 
 from ..compat import compat_urlparse
 from .common import InfoExtractor
 
-FormatData = namedtuple('FormatData', [
-    'format_id', 'sub_domain', 'ext', 'quality'])
-
 
 class JamendoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
     _TEST = {
         'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
         'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
@@ -26,36 +22,31 @@ class JamendoIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        url_data = self._VALID_URL_RE.match(url)
+        mobj = self._VALID_URL_RE.match(url)
-        track_id = url_data.group('id')
+        track_id = mobj.group('id')
-        display_id = url_data.group('display_id')
+        display_id = mobj.group('display_id')
+
         webpage = self._download_webpage(url, display_id)
 
+        title = self._html_search_meta('name', webpage, 'title')
+
+        formats = [{
+            'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
+                   % (sub_domain, track_id, format_id),
+            'format_id': format_id,
+            'ext': ext,
+            'quality': quality,
+        } for quality, (format_id, sub_domain, ext) in enumerate((
+            ('mp31', 'mp3l', 'mp3'),
+            ('mp32', 'mp3d', 'mp3'),
+            ('ogg1', 'ogg', 'ogg'),
+            ('flac', 'flac', 'flac'),
+        ))]
+        self._sort_formats(formats)
+
         thumbnail = self._html_search_meta(
             'image', webpage, 'thumbnail', fatal=False)
-        title = self._html_search_meta('name', webpage, 'title')
 
-        url_template = 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
-        format_data = [
-            FormatData(
-                format_id='mp31', sub_domain='mp3l', ext='mp3', quality=0),
-            FormatData(
-                format_id='mp32', sub_domain='mp3d', ext='mp3', quality=1),
-            FormatData(
-                format_id='ogg1', sub_domain='ogg', ext='ogg', quality=2),
-            FormatData(
-                format_id='flac', sub_domain='flac', ext='flac', quality=3),
-        ]
-        formats = [
-            {
-                'format_id': fd.format_id,
-                'url': url_template % (fd.sub_domain, track_id, fd.format_id),
-                'ext': fd.ext,
-                'quality': fd.quality
-            }
-            for fd in format_data
-        ]
-        self._check_formats(formats, video_id=display_id)
         return {
             'id': track_id,
             'display_id': display_id,
@@ -73,45 +64,44 @@ class JamendoAlbumIE(InfoExtractor):
             'id': '121486',
             'title': 'Duck On Cover'
         },
-        'playlist_mincount': 2,
+        'playlist': [{
-        'playlist': [
+            'md5': 'e1a2fcb42bda30dfac990212924149a8',
-            {
+            'info_dict': {
-                'md5': 'e1a2fcb42bda30dfac990212924149a8',
+                'id': '1032333',
-                'info_dict': {
+                'ext': 'flac',
-                    'id': '1032333',
+                'title': 'Warmachine'
-                    'ext': 'flac',
+            }
-                    'title': 'Warmachine'
+        }, {
-                }
+            'md5': '1f358d7b2f98edfe90fd55dac0799d50',
-            },
+            'info_dict': {
-            {
+                'id': '1032330',
-                'md5': '1f358d7b2f98edfe90fd55dac0799d50',
+                'ext': 'flac',
-                'info_dict': {
+                'title': 'Without Your Ghost'
-                    'id': '1032330',
-                    'ext': 'flac',
-                    'title': 'Without Your Ghost'
-                }
             }
-        ],
+        }],
         'params': {
             'playlistend': 2
         }
     }
 
     def _real_extract(self, url):
-        url_data = self._VALID_URL_RE.match(url)
+        mobj = self._VALID_URL_RE.match(url)
-        album_id = url_data.group('id')
+        album_id = mobj.group('id')
-        webpage = self._download_webpage(url, url_data.group('display_id'))
+
+        webpage = self._download_webpage(url, mobj.group('display_id'))
 
         title = self._html_search_meta('name', webpage, 'title')
 
-        track_paths = re.findall(r'<a href="(.+)" class="link-wrap js-trackrow-albumpage-link" itemprop="url">', webpage)
         entries = [
-            self.url_result(compat_urlparse.urljoin(url, path), ie=JamendoIE.ie_key())
+            self.url_result(
-            for path in track_paths
+                compat_urlparse.urljoin(url, m.group('path')),
+                ie=JamendoIE.ie_key(),
+                video_id=self._search_regex(
+                    r'/track/(\d+)', m.group('path'),
+                    'track id', default=None))
+            for m in re.finditer(
+                r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
+                webpage)
         ]
-        return {
+
-            '_type': 'playlist',
+        return self.playlist_result(entries, album_id, title)
-            'id': album_id,
-            'title': title,
-            'entries': entries
-        }